Semantic Representations for Interactive Text Mining
交互式文本挖掘的语义表示
基本信息
- 批准号:RGPIN-2020-04834
- 负责人:
- 金额:$ 2.55万
- 依托单位:
- 依托单位国家:加拿大
- 项目类别:Discovery Grants Program - Individual
- 财政年份:2021
- 资助国家:加拿大
- 起止时间:2021-01-01 至 2022-12-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Key limitations of today's knowledge workers, whose job involves handling or using information, include (a) the amount of text they have to read and digest, and (b) the amount of time they spend searching for, gathering and organizing information in text form. Examples of text-intensive tasks on specialized corpora include: literature search on a given topic for compilation of a systematic review; high-recall retrieval of patents, court decisions or incident reports in customer service or online communities; search and browsing of electronic medical records or health-related listserver content for tacit knowledge embedded in free text; and annotation of papers with research topics. Examples of informal text such as social media include rumour detection and propagation, dynamic topic detection and tracking, and analysis of interviews in sociology research. Core research problems underlying these use cases include: (1) Semantic retrieval of documents, addressing vocabulary mismatch across related documents; (2) The exploitation of semi-structured knowledge bases, such as Wikipedia, as well as weakly organized domain-specific corpora; (3) Handling the dynamic nature of the text data, including concept drift, and flexibly handling shorter or longer time frames; (4) The need for the human-in-the-loop text mining, to guide the algorithms towards producing relevant results for the individual user. This requires interactive visualizations and algorithms open to user interaction. Semantic relatedness methods have been proposed based on word and document embeddings derived from unsupervised training of various deep network architectures on tasks such as word or sentence prediction in large text corpora. Such embeddings have demonstrated advances to the state of the art on a number of supervised downstream natural language processing tasks. However, a gap exists between semantic text representations based on embeddings, which are dense numeric vectors, and human intuition, whose elicitation requires interactive visual interfaces to involve a non-technical user effectively. The proposed research will aim to fill this gap by focusing on explainable, as opposed to black box, machine learning algorithms and representations. Taking this one step further, we will build on interactivity to achieve explainability, allowing the human to efficiently steer the machine learning towards meaningful results. Overall, we will aim for the next-generation visual text analytics systems that build on the capabilities of modern word, term and document embeddings based on deep networks to capture semantics better than the bag-of-words representations, without losing the intuitive nature of word- and term-based visualizations. The proposed research will be a contribution to the emerging research area of explainable deep networks, specialized to interactive machine learning for supporting knowledge workers.
当今知识工作者的工作涉及处理或使用信息,其主要局限性包括:(a)他们必须阅读和消化的文本量,以及(B)他们花在搜索、收集和组织文本形式的信息上的时间量。专门语料库上的文本密集型任务的例子包括:为编写系统综述而对给定主题进行文献检索;在客户服务或在线社区中对专利、法院判决或事件报告进行高召回率检索;搜索和浏览电子病历或与健康相关的列表服务器内容,以寻找自由文本中嵌入的隐性知识;以及对论文进行研究主题注释。社交媒体等非正式文本的例子包括谣言检测和传播,动态主题检测和跟踪,以及社会学研究中的访谈分析。这些用例背后的核心研究问题包括:(1)文档的语义检索,解决相关文档之间的词汇不匹配问题;(2)半结构化知识库(如维基百科)以及弱组织的特定领域语料库的利用;(3)处理文本数据的动态特性,包括概念漂移,并灵活处理较短或较长的时间框架;(4)需要人在回路中的文本挖掘,以引导算法为个人用户产生相关结果。这需要交互式可视化和算法开放给用户交互。 语义相关性方法是基于单词和文档嵌入提出的,这些嵌入是从各种深度网络架构的无监督训练中获得的,用于大型文本语料库中的单词或句子预测等任务。这样的嵌入已经证明了在许多有监督的下游自然语言处理任务上的先进性。然而,基于嵌入的语义文本表示,这是密集的数字向量,和人类的直觉,其启发需要交互式的视觉界面,有效地涉及非技术用户之间存在差距。拟议的研究将旨在通过专注于可解释的机器学习算法和表示来填补这一空白,而不是黑箱。更进一步,我们将建立在交互性的基础上,以实现可解释性,使人类能够有效地引导机器学习获得有意义的结果。 总的来说,我们的目标是下一代视觉文本分析系统,该系统基于基于深度网络的现代单词,术语和文档嵌入的功能,以捕获比词袋表示更好的语义,而不会失去基于单词和术语的可视化的直观性。拟议的研究将有助于可解释深度网络的新兴研究领域,专门用于支持知识工作者的交互式机器学习。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Milios, Evangelos其他文献
Information retrieval by semantic similarity
- DOI:
10.4018/jswis.2006070104 - 发表时间:
2006-07-01 - 期刊:
- 影响因子:3.2
- 作者:
Hliaoutakis, Angelos;Varelas, Giannis;Milios, Evangelos - 通讯作者:
Milios, Evangelos
Causal graph extraction from news: a comparative study of time-series causality learning techniques.
- DOI:
10.7717/peerj-cs.1066 - 发表时间:
2022 - 期刊:
- 影响因子:3.8
- 作者:
Maisonnave, Mariano;Delbianco, Fernando;Tohme, Fernando;Milios, Evangelos;Maguitman, Ana G. - 通讯作者:
Maguitman, Ana G.
Improving the performance of focused web crawlers
- DOI:
10.1016/j.datak.2009.04.002 - 发表时间:
2009-10-01 - 期刊:
- 影响因子:2.5
- 作者:
Batsakis, Sotiris;Petrakis, Euripides G. M.;Milios, Evangelos - 通讯作者:
Milios, Evangelos
Statistical learning for OCR error correction
- DOI:
10.1016/j.ipm.2018.06.001 - 发表时间:
2018-11-01 - 期刊:
- 影响因子:8.6
- 作者:
Mei, Jie;Islam, Aminul;Milios, Evangelos - 通讯作者:
Milios, Evangelos
Topic-based web site summarization
- DOI:
10.1108/17440081011090220 - 发表时间:
2010-01-01 - 期刊:
- 影响因子:1.6
- 作者:
Zhang, Yongzheng;Milios, Evangelos;Zincir-Heywood, Nur - 通讯作者:
Zincir-Heywood, Nur
Milios, Evangelos的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Milios, Evangelos', 18)}}的其他基金
Semantic Representations for Interactive Text Mining
交互式文本挖掘的语义表示
- 批准号:
RGPIN-2020-04834 - 财政年份:2022
- 资助金额:
$ 2.55万 - 项目类别:
Discovery Grants Program - Individual
How is Canadians' mental health affected by COVID-19: visual analytics of social media text
COVID-19 对加拿大人的心理健康有何影响:社交媒体文本的可视化分析
- 批准号:
554657-2020 - 财政年份:2020
- 资助金额:
$ 2.55万 - 项目类别:
Alliance Grants
Semantic Representations for Interactive Text Mining
交互式文本挖掘的语义表示
- 批准号:
RGPIN-2020-04834 - 财政年份:2020
- 资助金额:
$ 2.55万 - 项目类别:
Discovery Grants Program - Individual
Exploiting Semantic Analysis of Documents
利用文档语义分析
- 批准号:
RGPIN-2015-06183 - 财政年份:2019
- 资助金额:
$ 2.55万 - 项目类别:
Discovery Grants Program - Individual
Semantic search using deep networks****
使用深度网络进行语义搜索****
- 批准号:
531051-2018 - 财政年份:2018
- 资助金额:
$ 2.55万 - 项目类别:
Engage Grants Program
Exploiting Semantic Analysis of Documents
利用文档语义分析
- 批准号:
RGPIN-2015-06183 - 财政年份:2018
- 资助金额:
$ 2.55万 - 项目类别:
Discovery Grants Program - Individual
Visual text analytics for total recall information retrieval in large noisy text datasets
用于大型噪声文本数据集中的总召回信息检索的视觉文本分析
- 批准号:
499941-2016 - 财政年份:2017
- 资助金额:
$ 2.55万 - 项目类别:
Collaborative Research and Development Grants
Exploiting Semantic Analysis of Documents
利用文档语义分析
- 批准号:
RGPIN-2015-06183 - 财政年份:2017
- 资助金额:
$ 2.55万 - 项目类别:
Discovery Grants Program - Individual
Trajectory-based localization using WiFi signal strength
使用 WiFi 信号强度进行基于轨迹的定位
- 批准号:
507295-2016 - 财政年份:2016
- 资助金额:
$ 2.55万 - 项目类别:
Engage Grants Program
Automation and Evaluation of Business Intelligence
商业智能的自动化和评估
- 批准号:
492547-2015 - 财政年份:2016
- 资助金额:
$ 2.55万 - 项目类别:
Engage Grants Program
相似海外基金
Promoting Students' Data Literacy through the Creation of Interactive Multimodal Representations of Biometric Data
通过创建生物识别数据的交互式多模态表示来提高学生的数据素养
- 批准号:
2241751 - 财政年份:2023
- 资助金额:
$ 2.55万 - 项目类别:
Standard Grant
Semantic Representations for Interactive Text Mining
交互式文本挖掘的语义表示
- 批准号:
RGPIN-2020-04834 - 财政年份:2022
- 资助金额:
$ 2.55万 - 项目类别:
Discovery Grants Program - Individual
Semantic Representations for Interactive Text Mining
交互式文本挖掘的语义表示
- 批准号:
RGPIN-2020-04834 - 财政年份:2020
- 资助金额:
$ 2.55万 - 项目类别:
Discovery Grants Program - Individual
Mathematical Foundations of Multiscale Graph Representations and Interactive Learning
多尺度图表示和交互式学习的数学基础
- 批准号:
0808847 - 财政年份:2008
- 资助金额:
$ 2.55万 - 项目类别:
Standard Grant
The use of graphical representations to scaffold collaborative argumentation around an interactive whiteboard in Key Stage 2 science
在关键阶段 2 科学中使用图形表示来围绕交互式白板进行协作论证
- 批准号:
ES/F017731/1 - 财政年份:2008
- 资助金额:
$ 2.55万 - 项目类别:
Research Grant
HCC: Interactive and Enriched Haptic Graphical Representations for People who are Blind and Visually Impaired
HCC:为盲人和视障人士提供丰富的交互式触觉图形表示
- 批准号:
0712936 - 财政年份:2007
- 资助金额:
$ 2.55万 - 项目类别:
Continuing Grant
Central representations of interactive tasks
交互任务的中心表示
- 批准号:
184016-1996 - 财政年份:1999
- 资助金额:
$ 2.55万 - 项目类别:
Discovery Grants Program - Individual
Algorithms and Geometry Representations for Interactive Visualization and Modeling
用于交互式可视化和建模的算法和几何表示
- 批准号:
9978147 - 财政年份:1999
- 资助金额:
$ 2.55万 - 项目类别:
Standard Grant
Central representations of interactive tasks
交互任务的中心表示
- 批准号:
184016-1996 - 财政年份:1998
- 资助金额:
$ 2.55万 - 项目类别:
Discovery Grants Program - Individual
Central representations of interactive tasks
交互任务的中心表示
- 批准号:
184016-1996 - 财政年份:1997
- 资助金额:
$ 2.55万 - 项目类别:
Discovery Grants Program - Individual